← Back to all news

Inference efficiency

Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.

6,043 stories · RSS feed

arXiv Machine Learning
Sep 10

MILAAP: Mobile Link Allocation via Attention-based Prediction

The paper introduces MiLAAP, an attention‑based framework that predicts channel occupancy and node motion in channel‑hopping communication systems without exchanging state information. By leveraging self‑attention and multi‑head attention, each node passively observes local channel activity to forecast interference patterns and mobility, achieving near‑perfect prediction accuracy across varied mobility scenarios and demonstrating zero‑shot generalizability to new channel‑sequence periods.

By Yung-Fu Chen, Anish Arora
efficiency
More like this →
arXiv AI
Sep 10

Agentic ML Exploration (A-MLE) for Ads Ranking

arXiv:2609.08248v1 Announce Type: new Abstract: Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iterati...

By Erwin Gao, Vinodh Kumar Sunkara, Jingyi Guan, Qinjin Jia, Hangjun Xu, Xiang Ji, Sherman Wong, Surya Teja Chavali, Pratik Vaishnavi, Aryan Pandhi, Xiaoyu Deng, Zhaodong Wang, Samarth Inani, Fan Yang, Jakob Moberg, Zoe Zu, Nicolas Bievre, Sami Khenissi, Amit Jaspal, Ehsan Fakharizadi, Srinidhi Viswanathan, Dorothy Sun, Abishek Vanam, Sneha Iyer, Sheela Yadawad, Wenjie Chen, Gaby Nahum, Junhua Gu, Peter Chu, Yucheng Liu, Xin Zhao, Vitor Cid, Chaorong Chen, Vijay Pappu, Ashwin Kumar, Wenlin Chen, Ben Schulte, Deepak Chandra, Ritwik Tewari
llmsagentsefficiency
More like this →
arXiv AI
Sep 10

Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs

The paper argues that relying solely on zero‑shot task accuracy is insufficient for evaluating quantized large language models (LLMs) because accuracy ignores changes in the full predictive distribution. It proposes a distribution‑sensitive framework that measures fidelity loss by computing statistical distances—such as Jensen‑Shannon Divergence and Total Variation Distance—between the full‑vocabulary output distributions of a full‑precision BF16 reference and its quantized counterparts. Experiments across five foundation architectures and four reasoning benchmarks show that these divergence metrics increase with stronger quantization, revealing distributional drift that top‑1 accuracy fails to capture, and suggest that mixed‑precision Q4_K schemes can offer lower divergence than uniform Q4_0 at comparable memory usage.

By Shahzeb Qamar, Lorenz Sparrenberg, Christian Bauckhage, Baha Rababah, Carson Leung, Murat Kantarcioglu, Cuneyt Gurcan Akcora, Rafet Sifa
llmsefficiencybenchmarkssafety
More like this →
arXiv AI
Sep 10

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

A*-Thought-V2 is a framework that models Chain-of-Thought reasoning as a geometric trajectory in a 3D PCA space, using explicit-implicit latent tokens to compress steps that deviate from the main question-to-solution direction. The method measures alignment angles to decide which steps remain text and which become latent, and introduces stepwise embedding forcing and label forcing to train the architecture. Experiments on Qwen models show up to 2.6% accuracy gains, halved response length, and significant reductions in computation and training time.

By Xiaoang Xu, Siyuan Liu, Shuo Wang, Junlan Feng, Fanyu Meng, Zhu Zhang, Jixun Wang, Xiaorong Wang, Zihan Zhou, Xin Li, Chaojun Xiao, Yiming Zhang, Huijia Wu, Liuyu Xiang, Peipei Li, Zhaofeng He
llmsragefficiencymultimodalbenchmarkssafety
More like this →
arXiv AI
Sep 10

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

The paper introduces Vision-of-Thought (VoT), a framework that inserts a discrete visual-thinking layer between vision‑language models (VLMs) and diffusion transformers (DiTs). Instead of using VLMs solely as text encoders, they act as multimodal planners that generate VoT tokens—high‑level visual plans such as objects and layouts—before pixel rendering. A specialized VoT tokenizer is trained with a closed‑loop objective combining VLM alignment, feature reconstruction, and vector‑quantization losses, ensuring the tokens are semantically readable by the VLM while preserving necessary visual information. Experimental results show that VoT improves semantic alignment and offers a structured, interpretable interface for controllable generation.

By Jingxiang Sun, Chao Liao, Zhengxiong Luo, Chaorui Deng, Chen-lin Zhang, Junke Wang, Ceyuan Yang, Haoqi Fan, Weilin Huang
llmsdiffusionnlpefficiencymultimodalsafety
More like this →
arXiv AI
Sep 10

Reason Through the Latent! Making Latent Visual Reasoning Necessary

The paper introduces Causal Visual Recurrent Reasoning (CVRR), a method that forces multimodal models to rely on latent visual states by using recurrent computation as the sole image‑conditioned path to prediction. CVRR initializes recurrence from the question hidden state after a pretrained vision‑language model has processed the image, repeatedly updates this state while re‑reading the same visual evidence, and removes all other visual traces before decoding. Experiments on several benchmarks show that CVRR maintains strong performance while other latent reasoners lose visual competence, and causal interventions confirm that predictions depend on the recurrent visual trajectory.

By Suhyeong Park, Junha Jung, Jaewoo Kang
llmsefficiencymultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 10

Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?

The paper addresses the challenge of long input contexts in Retrieval-Augmented Generation (RAG) systems, where concatenating many retrieved chunks increases prefill workload and time to first token (TTFT). It proposes a dual strategy: fine‑tuning the model to be aware of KV cache concatenation and selectively recomputing only part of the KV caches. Experiments on the RULER benchmark show that for a 124k‑token input, this combined method boosts the RULER score by 9.7 points over a baseline that recomputes caches only, while cutting TTFT by 80% compared with full attention.

By Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi
ragfine-tuningefficiencybenchmarks
More like this →